forked from phoenix-oss/llama-stack-mirror
8b655e3cd2
# What does this PR do? - Update `/eval-tasks` to `/benchmarks` - ⚠️ Remove differentiation between `app` v.s. `benchmark` eval task config. Now we only have `BenchmarkConfig`. The overloaded `benchmark` is confusing and do not add any value. Backward compatibility is being kept as the "type" is not being used anywhere. [//]: # (If resolving an issue, uncomment and update the line below) [//]: # (Closes #[issue-number]) ## Test Plan - This change is backward compatible - Run notebook test with ``` pytest -v -s --nbval-lax ./docs/getting_started.ipynb pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb ``` <img width="846" alt="image" src="https://github.com/user-attachments/assets/d2fc06a7-593a-444f-bc1f-10ab9b0c843d" /> [//]: # (## Documentation) [//]: # (- [ ] Added a Changelog entry if the change is significant) --------- Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com> Signed-off-by: Ben Browning <bbrownin@redhat.com> Signed-off-by: Sébastien Han <seb@redhat.com> Signed-off-by: reidliu <reid201711@gmail.com> Co-authored-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com> Co-authored-by: Ben Browning <ben324@gmail.com> Co-authored-by: Sébastien Han <seb@redhat.com> Co-authored-by: Reid <61492567+reidliu41@users.noreply.github.com> Co-authored-by: reidliu <reid201711@gmail.com> Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
69 lines
1.9 KiB
Python
69 lines
1.9 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import importlib
|
|
from typing import Dict, List
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.providers.datatypes import Api, ProviderSpec
|
|
|
|
|
|
def stack_apis() -> List[Api]:
|
|
return [v for v in Api]
|
|
|
|
|
|
class AutoRoutedApiInfo(BaseModel):
|
|
routing_table_api: Api
|
|
router_api: Api
|
|
|
|
|
|
def builtin_automatically_routed_apis() -> List[AutoRoutedApiInfo]:
|
|
return [
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.models,
|
|
router_api=Api.inference,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.shields,
|
|
router_api=Api.safety,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.vector_dbs,
|
|
router_api=Api.vector_io,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.datasets,
|
|
router_api=Api.datasetio,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.scoring_functions,
|
|
router_api=Api.scoring,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.benchmarks,
|
|
router_api=Api.eval,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.tool_groups,
|
|
router_api=Api.tool_runtime,
|
|
),
|
|
]
|
|
|
|
|
|
def providable_apis() -> List[Api]:
|
|
routing_table_apis = set(x.routing_table_api for x in builtin_automatically_routed_apis())
|
|
return [api for api in Api if api not in routing_table_apis and api != Api.inspect]
|
|
|
|
|
|
def get_provider_registry() -> Dict[Api, Dict[str, ProviderSpec]]:
|
|
ret = {}
|
|
for api in providable_apis():
|
|
name = api.name.lower()
|
|
module = importlib.import_module(f"llama_stack.providers.registry.{name}")
|
|
ret[api] = {a.provider_type: a for a in module.available_providers()}
|
|
|
|
return ret
|